{"id":"W4372260056","doi":"10.1109/icassp49357.2023.10095934","title":"On Weighted Cross-Entropy for Label-Imbalanced Separable Data: An Algorithmic-Stability Study","year":2023,"lang":"en","type":"article","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Early stopping; Generalization error; Logarithm; Cross entropy; Gradient descent; Conjecture; Mathematics; Algorithm; Regularization (linguistics); Applied mathematics; Stability (learning theory); Artificial intelligence; Machine learning; Pattern recognition (psychology); Artificial neural network; Discrete mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001394277,0.000163486,0.0002054353,0.0001042523,0.0003679327,0.0005099051,0.001456227,0.00004859619,0.0001024128],"category_scores_gemma":[0.0001796213,0.0001408607,0.00003386969,0.0007284082,0.00003911516,0.001069221,0.0003757164,0.000138748,0.0002958813],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004408462,"about_ca_system_score_gemma":0.00007143274,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003861487,"about_ca_topic_score_gemma":0.00004056407,"domain_scores_codex":[0.9978096,0.0001524001,0.000295095,0.0009195412,0.0003879398,0.0004353969],"domain_scores_gemma":[0.9976375,0.0003679767,0.00008097409,0.00162498,0.0001406613,0.0001479641],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001168675,0.01226746,0.07261725,0.0002034353,0.0005773847,0.0002096324,0.02214796,0.00965866,0.008414517,0.4996157,0.05728855,0.3158308],"study_design_scores_gemma":[0.002163487,0.0005810272,0.01429696,0.000003767008,0.000004935918,9.197769e-7,0.0004159839,0.9712591,0.0003491023,0.003953243,0.006746596,0.0002248465],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3478799,0.000007301529,0.6470169,0.0004004431,0.0006703486,0.0009689835,0.00004053149,0.001249111,0.001766503],"genre_scores_gemma":[0.9190605,0.000004062033,0.0753839,0.0005330999,0.0001148765,0.0001027044,0.000209569,0.000024905,0.004566423],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9616005,"threshold_uncertainty_score":0.5744132,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1096811870986246,"score_gpt":0.3856051661873163,"score_spread":0.2759239790886917,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}